Skip to content

to_base_variable: coerce multiindex data to numpy array #8888

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

to_base_variable: coerce multiindex data to numpy array #8888

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
c39b82a
to_base_variable: convert multiindex -> np.ndarray
benbovy Mar 29, 2024
0fb6c8f
add reset_index test
benbovy Mar 29, 2024
dd9c3b4
Add consistency check
dcherian Mar 29, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 7 additions & 1 deletion xarray/core/variable.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@
BasicIndexer,
OuterIndexer,
PandasIndexingAdapter,
PandasMultiIndexingAdapter,
VectorizedIndexer,
as_indexable,
)
Expand Down Expand Up @@ -530,8 +531,13 @@ def values(self, values):

def to_base_variable(self) -> Variable:
"""Return this variable as a base xarray.Variable"""
if isinstance(self._data, PandasMultiIndexingAdapter):
data = np.asarray(self._data)
else:
data = self._data

return Variable(
self._dims, self._data, self._attrs, encoding=self._encoding, fastpath=True
self._dims, data, self._attrs, encoding=self._encoding, fastpath=True
)

to_variable = utils.alias(to_base_variable, "to_variable")
Expand Down
17 changes: 17 additions & 0 deletions xarray/tests/test_dataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3514,6 +3514,20 @@ def test_reset_index(self) -> None:
with pytest.raises(ValueError, match=r".*not coordinates with an index"):
ds.reset_index("y")

def test_reset_multi_index_resets_levels(self) -> None:
# ND DataArray that gets stacked along a multiindex
da = DataArray(np.ones((3, 3)), coords={"dim1": [1, 2, 3], "dim2": [4, 5, 6]})
da = da.stack(feature=["dim1", "dim2"])

# Extract just the stacked coordinates for saving in a dataset
ds = Dataset(data_vars={"feature": da.feature})
xr.testing.assertions._assert_internal_invariants(
ds.reset_index(["feature", "dim1", "dim2"]), check_default_indexes=False
) # succeeds
xr.testing.assertions._assert_internal_invariants(
ds.reset_index(["feature"]), check_default_indexes=False
) # fails, but no warning either

def test_reset_index_keep_attrs(self) -> None:
coord_1 = DataArray([1, 2], dims=["coord_1"], attrs={"attrs": True})
ds = Dataset({}, {"coord_1": coord_1})
Expand Down Expand Up @@ -3560,6 +3574,9 @@ def test_reset_index_drop_convert(
assert name not in reset.variables
for name in converted:
assert_identical(reset[name].variable, ds[name].variable.to_base_variable())
# check that variable data is converted back to a numpy array
# (https://github.com/pydata/xarray/issues/8887)
assert isinstance(reset[name].variable._data, np.ndarray)
for old_name, new_name in renamed.items():
assert_identical(ds[old_name].variable, reset[new_name].variable)

Expand Down